根据customer_id取模切分orders表的数据
清除dn1上的orders、dict_order_type、orders_detail表
drop table if exists orders,dict_order_type,orders_detail;
vim schema.xml
<?xml version="1.0"?>
<!DOCTYPE mycat:schema SYSTEM "schema.dtd">
<mycat:schema xmlns:mycat="http://io.mycat/">
<schema name="TESTDB" checkSQLschema="false" sqlMaxLimit="100" dataNode='dn1'>
<table name='customer' dataNode='dn2'></table>
<table name='orders' dataNode='dn1,dn2' rule='mod_rule'></table> <!-- orders在两台主机上都要有,进行数据切片存储 -->
</schema>
<dataNode name="dn1" dataHost="host1" database="order190401" />
<dataNode name="dn2" dataHost="host2" database="order190401" />
<dataHost name="host1" maxCon="1000" minCon="10" balance="0"
writeType="0" dbType="mysql" dbDriver="native" switchType="1" slaveThreshold="100">
<heartbeat>select user()</heartbeat>
<!-- can have multi write hosts -->
<writeHost host="hostM1" url="192.168.78.120:3306" user="root"
password="root">
<!-- can have multi read hosts -->
</writeHost>
</dataHost>
<dataHost name="host2" maxCon="1000" minCon="10" balance="0"
writeType="0" dbType="mysql" dbDriver="native" switchType="1" slaveThreshold="100">
<heartbeat>select user()</heartbeat>
<!-- can have multi write hosts -->
<writeHost host="hostM2" url="192.168.78.121:3306" user="root"
password="root">
<!-- can have multi read hosts -->
</writeHost>
</dataHost>
</mycat:schema>
vim rule.xml
<?xml version="1.0" encoding="UTF-8"?>
<!-- - - Licensed under the Apache License, Version 2.0 (the "License");
- you may not use this file except in compliance with the License. - You
may obtain a copy of the License at - - http://www.apache.org/licenses/LICENSE-2.0
- - Unless required by applicable law or agreed to in writing, software -
distributed under the License is distributed on an "AS IS" BASIS, - WITHOUT
WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - See the
License for the specific language governing permissions and - limitations
under the License. -->
<!DOCTYPE mycat:rule SYSTEM "rule.dtd">
<mycat:rule xmlns:mycat="http://io.mycat/">
<tableRule name="mod_rule">
<rule>
<columns>customer_id</columns> <!-- 要和数据库表的字段名一样 -->
<algorithm>mod-long</algorithm> <!-- 指定数据切片的算法,这里mod-long" -->
</rule>
</tableRule>
<tableRule name="sharding-by-murmur">
<rule>
<columns>id</columns>
<algorithm>murmur</algorithm>
</rule>
</tableRule>
<tableRule name="crc32slot">
<rule>
<columns>id</columns>
<algorithm>crc32slot</algorithm>
</rule>
</tableRule>
<tableRule name="sharding-by-month">
<rule>
<columns>create_time</columns>
<algorithm>partbymonth</algorithm>
</rule>
</tableRule>
<tableRule name="latest-month-calldate">
<rule>
<columns>calldate</columns>
<algorithm>latestMonth</algorithm>
</rule>
</tableRule>
<tableRule name="auto-sharding-rang-mod">
<rule>
<columns>id</columns>
<algorithm>rang-mod</algorithm>
</rule>
</tableRule>
<tableRule name="jch">
<rule>
<columns>id</columns>
<algorithm>jump-consistent-hash</algorithm>
</rule>
</tableRule>
<function name="murmur"
class="io.mycat.route.function.PartitionByMurmurHash">
<property name="seed">0</property><!-- 默认是0 -->
<property name="count">2</property><!-- 要分片的数据库节点数量,必须指定,否则没法分片 -->
<property name="virtualBucketTimes">160</property><!-- 一个实际的数据库节点被映射为这么多虚拟节点,默认是160倍,也就是虚拟节点数是物理节点数的160倍 -->
<!-- <property name="weightMapFile">weightMapFile</property> 节点的权重,没有指定权重的节点默认是1。以properties文件的格式填写,以从0开始到count-1的整数值也就是节点索引为key,以节点权重值为值。所有权重值必须是正整数,否则以1代替 -->
<!-- <property name="bucketMapPath">/etc/mycat/bucketMapPath</property>
用于测试时观察各物理节点与虚拟节点的分布情况,如果指定了这个属性,会把虚拟节点的murmur hash值与物理节点的映射按行输出到这个文件,没有默认值,如果不指定,就不会输出任何东西 -->
</function>
<function name="crc32slot"
class="io.mycat.route.function.PartitionByCRC32PreSlot">
<property name="count">2</property><!-- 要分片的数据库节点数量,必须指定,否则没法分片 -->
</function>
<function name="hash-int"
class="io.mycat.route.function.PartitionByFileMap">
<property name="mapFile">partition-hash-int.txt</property>
</function>
<function name="rang-long"
class="io.mycat.route.function.AutoPartitionByLong">
<property name="mapFile">autopartition-long.txt</property>
</function>
<function name="mod-long" class="io.mycat.route.function.PartitionByMod"><!-- 将数值按主机数量取模,然后将数据根据模值分布到对应的主机上 -->
<!-- how many data nodes -->
<property name="count">2</property> <!-- 这里修改成咱们实际的主机数量 -->
</function>
<function name="func1" class="io.mycat.route.function.PartitionByLong">
<property name="partitionCount">8</property>
<property name="partitionLength">128</property>
</function>
<function name="latestMonth"
class="io.mycat.route.function.LatestMonthPartion">
<property name="splitOneDay">24</property>
</function>
<function name="partbymonth"
class="io.mycat.route.function.PartitionByMonth">
<property name="dateFormat">yyyy-MM-dd</property>
<property name="sBeginDate">2015-01-01</property>
</function>
<function name="rang-mod" class="io.mycat.route.function.PartitionByRangeMod">
<property name="mapFile">partition-range-mod.txt</property>
</function>
<function name="jump-consistent-hash" class="io.mycat.route.function.PartitionByJumpConsistentHash">
<property name="totalBuckets">3</property>
</function>
</mycat:rule>
启动mycat
./mycat console
创建orders表
# 连接mycat
mysql -umycat -p'123456' -P 8066 -h 192.168.78.120
-- 创建orders表
create table orders(
id int auto_increment,
order_type int,
customer_id int,
amount decimal(10,2),
primary key(id)
);
此时,dn1 、dn2主机上都已经创建好了orders表。
测试表的水平切分
此处请注意: 但凡使用mycat进行数据的插入,需要按照标准的sql写法(将表字段写明),否则mycat无法识别内容所对应的字段,既:必须是 insert into orders(id,order_type ,customer_id ,amount ) values(1,101,100,100100); 不能写成 insert into orders values(1,101,100,100100); 否则会报错,无法插入数据。
insert into orders(id,order_type ,customer_id ,amount ) values(1,101,100,100100);
insert into orders(id,order_type ,customer_id ,amount ) values(2,101,100,100300);
insert into orders(id,order_type ,customer_id ,amount ) values(3,101,101,120000);
insert into orders(id,order_type ,customer_id ,amount ) values(4,101,101,103000);
insert into orders(id,order_type ,customer_id ,amount ) values(5,102,101,100400);
insert into orders(id,order_type ,customer_id ,amount ) values(6,102,100,100020);
mysql> select * from orders;
+----+------------+-------------+-----------+
| id | order_type | customer_id | amount |
+----+------------+-------------+-----------+
| 3 | 101 | 101 | 120000.00 |
| 4 | 101 | 101 | 103000.00 |
| 5 | 102 | 101 | 100400.00 |
| 1 | 101 | 100 | 100100.00 |
| 2 | 101 | 100 | 100300.00 |
| 6 | 102 | 100 | 100020.00 |
+----+------------+-------------+-----------+
6 rows in set (0.00 sec)
mysql>
分别在dn1、dn2上查看:
可以看到customer_id为101的数据分布在dn2上,customer_id为100的数据分布在了dn1上,与预期的一致。
配置E-R表
由于不能跨库join,为了能够使orders和子表orders_detail进行关联查询,orders_detail也需要按照相应的规则(mycat会根据配置自动按照父表的分布规则)进行数据分布,mycat提供了E-R表配置的方式进行配置。
vim schema.xml
<schema name="TESTDB" checkSQLschema="false" sqlMaxLimit="100" dataNode='dn1'>
<table name='customer' dataNode='dn2'></table>
<table name='orders' dataNode='dn1,dn2' rule='mod_rule'>
<childTable name='orders_detail' primaryKey='id' joinKey='order_id' parentKey='id' /> <!-- 配置E-R表,子表与父表的关系 -->
</table>
</schema>
重启mycat
./mycat console
连接mycat,并创建orders_detail表
create table orders_detail(
id int auto_increment,
detail varchar(2000),
order_id int,
primary key(id)
);
插入数据
insert into orders_detail(id,detail,order_id) values(1,'detail',1);
insert into orders_detail(id,detail,order_id) values(2,'detail',2);
insert into orders_detail(id,detail,order_id) values(3,'detail',3);
insert into orders_detail(id,detail,order_id) values(4,'detail',4);
insert into orders_detail(id,detail,order_id) values(5,'detail',5);
insert into orders_detail(id,detail,order_id) values(6,'detail',6);
mysql> select * from orders_detail;
+----+--------+----------+
| id | detail | order_id |
+----+--------+----------+
| 1 | detail | 1 |
| 2 | detail | 2 |
| 6 | detail | 6 |
| 3 | detail | 3 |
| 4 | detail | 4 |
| 5 | detail | 5 |
+----+--------+----------+
6 rows in set (0.06 sec)
mysql>
-- 关联查询
mysql> select o.*,od.detail from orders o inner join orders_detail od on o.id=od.order_id;
+----+------------+-------------+-----------+--------+
| id | order_type | customer_id | amount | detail |
+----+------------+-------------+-----------+--------+
| 1 | 101 | 100 | 100100.00 | detail |
| 2 | 101 | 100 | 100300.00 | detail |
| 6 | 102 | 100 | 100020.00 | detail |
| 3 | 101 | 101 | 120000.00 | detail |
| 4 | 101 | 101 | 103000.00 | detail |
| 5 | 102 | 101 | 100400.00 | detail |
+----+------------+-------------+-----------+--------+
6 rows in set (0.04 sec)
mysql>
配置全局表(global / replication)
orders_detail表使用了字典表dict_order_type,所以,每台主机上都需要有dict_order_type所有的数据。
- 全局表一般不能是大数据表或者更新频繁的表,一般是字典表或系统表为宜。
- 全局表数据一般不大,就算有冗余,也不会对数据库性能产生大的影响。
vim schema.xml
<schema name="TESTDB" checkSQLschema="false" sqlMaxLimit="100" dataNode='dn1'>
<table name='customer' dataNode='dn2'></table>
<table name='orders' dataNode='dn1,dn2' rule='mod_rule'>
<childTable name='orders_detail' primaryKey='id' joinKey='order_id' parentKey='id' />
</table>
<table name='dict_order_type' dataNode='dn1,dn2' type='global' /> <!-- 配置全局表 -->
</schema>
重启mycat: ./mycat console
连接mycat,并创建表 dict_order_type ,插入数据
create table dict_order_type(
id int auto_increment,
order_type varchar(200),
primary key(id)
);
insert into dict_order_type(id,order_type) values(101,'type1');
insert into dict_order_type(id,order_type) values(102,'type2');
mysql> select * from dict_order_type; -- 全局表在每台主机上的数据都是一致的
+-----+------------+
| id | order_type |
+-----+------------+
| 101 | type1 |
| 102 | type2 |
+-----+------------+
2 rows in set (0.04 sec)
参考:https://www.bilibili.com/video/BV12b411K7Zu?p=349&spm_id_from=pageDriver